forked from tangger/lerobot
Add storage device configuration for SAC policy and replay buffer
- Introduce `storage_device` parameter in SAC configuration and training settings - Update learner server to use configurable storage device for replay buffer - Reduce online buffer capacity in ManiSkill configuration - Modify replay buffer initialization to support custom storage device
This commit is contained in:
committed by
Michel Aractingi
parent
ae51c19b3c
commit
bb69cb3c8c
@@ -20,6 +20,9 @@ training:
|
||||
grad_clip_norm: 10.0
|
||||
lr: 3e-4
|
||||
|
||||
|
||||
storage_device: "cpu"
|
||||
|
||||
eval_freq: 2500
|
||||
log_freq: 10
|
||||
save_freq: 2000000
|
||||
@@ -30,7 +33,7 @@ training:
|
||||
online_steps_between_rollouts: 1000
|
||||
online_sampling_ratio: 1.0
|
||||
online_env_seed: 10000
|
||||
online_buffer_capacity: 1000000
|
||||
online_buffer_capacity: 200000
|
||||
online_buffer_seed_size: 0
|
||||
online_step_before_learning: 500
|
||||
do_online_rollout_async: false
|
||||
|
||||
Reference in New Issue
Block a user